Jakob WennbergandClaude Fable 5
3d97b95197
Founder decision 2026-07-20: the three claude.ai cloud triggers ran for 19 days as silent no-ops (GH_TOKEN never provisioned, issue #993) and were disabled instead of provisioned. loops.md and loop-ignite now document local-only operation so future sessions do not re-enable the dead triggers or re-ask for provisioning. Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
2.4 KiB
name, description
| name | description |
|---|---|
| loop-ignite | Verify the agentic loops are actually running and ignite any that are not. Use at the start of any session, or whenever the user manually asks to "check the pr comments" / check logs / triage issues, which signals a loop is not firing. The loops are LOCAL-only since 2026-07-20 (cloud routines retired); the historical failure mode is that nobody initiates them. |
loop-ignite
Goal: the user never has to type "check the pr comments" again. That prompt was typed 323 times between 2026-04 and 2026-07; the loops that replace it were built 2026-07-01. This skill closes the initiation gap.
Cloud routines are RETIRED (founder decision 2026-07-20). The three claude.ai triggers (trig_01J2nG7eB9gsdAb9YSGBVwa8, trig_014CmE3gTJ7ErnvL2trPYymu, trig_017hB94ieGVwreJqHpGRDVoM) fired daily for 19 days as silent no-ops (no GH_TOKEN in the cloud env, issue #993) and were deliberately disabled instead of provisioned. Do NOT re-enable or re-create them; ignore them in audits. All loops run locally now.
When invoked
- Audit what is live.
- Local schedule:
CronListfor session-local jobs invoking/loop-*skills. - Evidence of firing: recent
loop/*branches, PR comments by the loop,loop:needs-humanlabels (gh pr list,gh issue list --label loop:needs-human).
- Local schedule:
- Report a one-screen status table: loop, expected cadence, last observed run, verdict (LIVE / DEAD / NEVER RAN).
- Ignite what is dead. For each non-live loop:
- Run the loop skill once NOW (
/loop-pr-ci-triage,/loop-issue-triage,/loop-vercel-errors) so the backlog is cleared this session. - Then schedule a session-local cadence (
CronCreateinvoking the matching/loop-*skill) and say clearly that it only runs while this session is alive (7-day auto-expiry). - If a loop cannot run at all, file the blocker as a GitHub issue so the gap is visible instead of silent.
- Run the loop skill once NOW (
- Switch-on check (mandatory): after igniting, verify via
CronListthat the jobs exist. End with either "ALL LOOPS LIVE (session-local)" or "NOT SWITCHED ON YET: - <what remains, who flips it>".
If the user manually types a loop-shaped request
("check the pr comments", "check the vercel/supabase logs for errors", "triage the issues") Do the requested work, then ALSO run the audit above and tell the user which loop should have made the request unnecessary, and whether it is now live.